© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1556
    Prev
    Next
    INDEX
    Explanations

    phrases related to online content and job postings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    username or commenter names followed by timestamps or metadata markers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⤹
    -0.56
    StoryboardSegue
    -0.55
    ➯
    -0.51
    principalTable
    -0.50
     kasarigan
    -0.50
     nakalista
    -0.50
    RectangleBorder
    -0.49
    verwijspagina
    -0.48
    esca
    -0.48
    homonymie
    -0.48
    POSITIVE LOGITS
    Jul
    0.66
     Jul
    0.65
     Sep
    0.64
     Oct
    0.63
     Feb
    0.61
     Apr
    0.61
     Aug
    0.61
     Jun
    0.60
    Sep
    0.57
    Apr
    0.57
    Activations Density 0.433%

    No Known Activations